Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Review Findings — measured AI agent skill | DecimalAI

davepoon/review-findings

SkillScore86Maintained

Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and prepares for re-verification. Delegates to the Forja (Dev) agent.

by davepoon

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

decimalai skills pull davepoon-review-findings

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/davepoon-review-findings/SKILL.md

Raw file: /s/davepoon-review-findings/SKILL.md ↗ · machine-readable summary at /s/davepoon-review-findings.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 12h ago

—-11% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	237%	0%
case-11	✗→✓	▲ Improved	-1%	0%
case-13	✗→✓	▲ Improved	-53%	0%
case-15	✗→✓	▲ Improved	-39%	0%
case-17	✗→✓	▲ Improved	-31%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

davepoon / buildwithclaude

plugins/agent-triforce/skills/review-findings/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Review Findings

Addresses and fixes QA findings using the Forja (Dev) agent.

When to Use This Skill

After receiving a code review from Centinela (QA)
When a review report has findings that need to be addressed
Fixing critical and warning issues before re-verification

What This Skill Does

Runs the SIGN IN checklist
Reads the review report and understands each finding's root cause
Plans fix order: Critical first, then Warnings
Implements fixes with updated tests for each finding
Scans for dead code after all fixes
Runs Implementation Complete and Pre-Delivery checklists (TIME OUT)
Verifies every Critical finding addressed, every Warning addressed or deferred with justification
Prepares a fix report for QA re-verification

How to Use

Basic Usage

/review-findings

With Specific Review

/review-findings docs/reviews/user-auth-review.md

Example

User: /review-findings docs/reviews/webhook-system-review.md

Output:

All Critical findings fixed with tests
All Warning findings fixed or explicitly deferred with justification
Fix report documenting what was changed and why
Ready for QA re-verification

Tips

If no review is specified, the most recent review in docs/reviews/ is used
The agent understands root causes before writing any fix
Conflicting fixes are identified and planned around during the pre-fix phase

Want to see if davepoon/review-findings would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.